© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12436
    Prev
    Next
    INDEX
    Explanations

    [article] [noun]

    np_acts-logits-general · gemini-2.5-flash-lite

    a followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    8
    0.95
    6
    0.92
    is
    0.89
    1
    0.88
    7
    0.88
     to
    0.84
    to
    0.84
    5
    0.82
    in
    0.81
    9
    0.77
    POSITIVE LOGITS
     tohoto
    0.79
     solchen
    0.67
     probleme
    0.63
    ことを
    0.61
     этом
    0.61
     товара
    0.60
     yerde
    0.59
     რომელი
    0.59
    இதில்
    0.58
     quelconque
    0.57
    Activations Density 1.950%

    No Known Activations